{"id":24938607,"url":"https://github.com/minitechy/betavae_recon","last_synced_at":"2025-07-02T13:33:51.890Z","repository":{"id":187947709,"uuid":"675505070","full_name":"Minitechy/betaVAE_recon","owner":"Minitechy","description":"Augmenting Reconstruction Accuracy in beta-VAE Model through Linear Gaussian Framework","archived":false,"fork":false,"pushed_at":"2023-08-12T21:58:17.000Z","size":1245,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T17:24:45.090Z","etag":null,"topics":["beta-vae","machine-learning","nonlinear-optimization","numerical-analysis"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Minitechy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-08-07T04:41:33.000Z","updated_at":"2024-02-20T07:54:53.000Z","dependencies_parsed_at":"2023-08-12T22:36:21.522Z","dependency_job_id":null,"html_url":"https://github.com/Minitechy/betaVAE_recon","commit_stats":null,"previous_names":["minitechy/beta-vae","minitechy/betavae_recon"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minitechy%2FbetaVAE_recon","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minitechy%2FbetaVAE_recon/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minitechy%2FbetaVAE_recon/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Minitechy%2FbetaVAE_recon/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Minitechy","download_url":"https://codeload.github.com/Minitechy/betaVAE_recon/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246068279,"owners_count":20718503,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["beta-vae","machine-learning","nonlinear-optimization","numerical-analysis"],"created_at":"2025-02-02T17:59:04.291Z","updated_at":"2025-03-28T17:24:50.827Z","avatar_url":"https://github.com/Minitechy.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Abstract:\nVariational Autoencoders (VAEs) have garnered substantial attention as generative models for producing lower-dimensional representations of high-dimensional data. The $\\beta$-VAE model employs the hyperparameter $\\beta$ to strike a balance between reconstruction accuracy and disentanglement. This study exclusively targets the enhancement of reconstruction accuracy in the linear Gaussian $\\beta$-VAE model by introducing three variants: $\\gamma$-VAE with both arbitrary and diagonalized $\\Sigma_{Z}$, as well as $\\gamma\\lambda$-VAE with diagonalized $\\Sigma_{Z}$. We commence by deriving closed-form solutions for all three proposed frameworks using gradient-based and iterative methods. This demonstration of consistency between approaches highlights the robustness of our findings. Subsequently, we perform comprehensive numerical experiments employing the Blahut-Arimoto algorithm. These experiments underscore the benefits of utilizing a diagonalized positive definite $\\Sigma_{Z}$ over an arbitrary one, leading to more informative numerical outcomes and augmented control over reconstruction accuracy. Furthermore, the introduction of an additional hyperparameter $\\lambda$ offers an avenue for further refining reconstruction accuracy control. In conclusion, the introduction of these three variants to the $\\beta$-VAE model, combined with analytical and numerical analyses, underscores the potential for improved reconstruction accuracy through the strategic incorporation of additional hyperparameters and nuanced adjustments to the foundational framework.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminitechy%2Fbetavae_recon","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fminitechy%2Fbetavae_recon","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminitechy%2Fbetavae_recon/lists"}